Lightweighting the prediction process of urban states with parameter sharing and dilated operations

Lightweight and high-precision prediction models for urban states are anticipated to run efficiently on resource-limited devices, serving as key technologies for realizing smart city management. However, many existing models, despite achieving high prediction precision, suffer from overly complex de...

Full description

Saved in:
Bibliographic Details
Main Authors: Peixiao Wang, Haolong Yang, Hengcai Zhang, Shifen Cheng, Feng Lu, Zeqiang Chen
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2025.2468414
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224298410016768
author Peixiao Wang
Haolong Yang
Hengcai Zhang
Shifen Cheng
Feng Lu
Zeqiang Chen
author_facet Peixiao Wang
Haolong Yang
Hengcai Zhang
Shifen Cheng
Feng Lu
Zeqiang Chen
author_sort Peixiao Wang
collection DOAJ
description Lightweight and high-precision prediction models for urban states are anticipated to run efficiently on resource-limited devices, serving as key technologies for realizing smart city management. However, many existing models, despite achieving high prediction precision, suffer from overly complex designs, leading to low computational efficiency, a large number of learnable parameters, and difficulty in hyper-parameter calibration. In this study, we present a lightweight parameter-shared dilated convolutional network (PSDCN) to address these challenges. Specifically, we define parameter-shared temporal/graph dilated convolution operators to efficiently and accurately capture spatio-temporal correlations without significantly increasing model's computation time and scale of learnable parameters. Furthermore, we establish mathematical relationships between hyperparameters, significantly reducing their number and simplifying the calibration process. The PSDCN model was validated using PM2.5, traffic, and temperature datasets. The results demonstrated that the PSDCN model simplifies hyperparameter calibration. It also either outperforms or matches the prediction accuracy of nine baselines, while achieving better time efficiency and requiring fewer learnable parameters.
format Article
id doaj-art-70ea24b56b6e4e1db4f4f04afdf6d7fa
institution Kabale University
issn 1753-8947
1753-8955
language English
publishDate 2025-08-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-70ea24b56b6e4e1db4f4f04afdf6d7fa2025-08-25T11:31:31ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2468414Lightweighting the prediction process of urban states with parameter sharing and dilated operationsPeixiao Wang0Haolong Yang1Hengcai Zhang2Shifen Cheng3Feng Lu4Zeqiang Chen5State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing, People’s Republic of ChinaGina Cody School of Engineering and Computer Science, Concordia University, Montreal, CanadaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing, People’s Republic of ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing, People’s Republic of ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing, People’s Republic of ChinaNational Engineering Research Center for Geographic Information System, China University of Geosciences, Wuhan, People’s Republic of ChinaLightweight and high-precision prediction models for urban states are anticipated to run efficiently on resource-limited devices, serving as key technologies for realizing smart city management. However, many existing models, despite achieving high prediction precision, suffer from overly complex designs, leading to low computational efficiency, a large number of learnable parameters, and difficulty in hyper-parameter calibration. In this study, we present a lightweight parameter-shared dilated convolutional network (PSDCN) to address these challenges. Specifically, we define parameter-shared temporal/graph dilated convolution operators to efficiently and accurately capture spatio-temporal correlations without significantly increasing model's computation time and scale of learnable parameters. Furthermore, we establish mathematical relationships between hyperparameters, significantly reducing their number and simplifying the calibration process. The PSDCN model was validated using PM2.5, traffic, and temperature datasets. The results demonstrated that the PSDCN model simplifies hyperparameter calibration. It also either outperforms or matches the prediction accuracy of nine baselines, while achieving better time efficiency and requiring fewer learnable parameters.https://www.tandfonline.com/doi/10.1080/17538947.2025.2468414Urban statesspatio-temporal predictiondilated operationparameter sharinghyper-parameter dependence
spellingShingle Peixiao Wang
Haolong Yang
Hengcai Zhang
Shifen Cheng
Feng Lu
Zeqiang Chen
Lightweighting the prediction process of urban states with parameter sharing and dilated operations
International Journal of Digital Earth
Urban states
spatio-temporal prediction
dilated operation
parameter sharing
hyper-parameter dependence
title Lightweighting the prediction process of urban states with parameter sharing and dilated operations
title_full Lightweighting the prediction process of urban states with parameter sharing and dilated operations
title_fullStr Lightweighting the prediction process of urban states with parameter sharing and dilated operations
title_full_unstemmed Lightweighting the prediction process of urban states with parameter sharing and dilated operations
title_short Lightweighting the prediction process of urban states with parameter sharing and dilated operations
title_sort lightweighting the prediction process of urban states with parameter sharing and dilated operations
topic Urban states
spatio-temporal prediction
dilated operation
parameter sharing
hyper-parameter dependence
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2468414
work_keys_str_mv AT peixiaowang lightweightingthepredictionprocessofurbanstateswithparametersharinganddilatedoperations
AT haolongyang lightweightingthepredictionprocessofurbanstateswithparametersharinganddilatedoperations
AT hengcaizhang lightweightingthepredictionprocessofurbanstateswithparametersharinganddilatedoperations
AT shifencheng lightweightingthepredictionprocessofurbanstateswithparametersharinganddilatedoperations
AT fenglu lightweightingthepredictionprocessofurbanstateswithparametersharinganddilatedoperations
AT zeqiangchen lightweightingthepredictionprocessofurbanstateswithparametersharinganddilatedoperations